Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8050
    Prev
    Next
    INDEX
    Explanations

    coding constructs and their respective attributes or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -0.41
    Rhestr
    -0.41
     يتيمه
    -0.40
    BagConstraints
    -0.39
    Personendaten
    -0.39
    المكان
    -0.37
     kaarangay
    -0.37
    gameserver
    -0.37
     argint
    -0.37
     ferons
    -0.36
    POSITIVE LOGITS
     x
    1.24
     X
    1.13
     y
    0.94
     Y
    0.91
    X
    0.87
     horizontal
    0.84
     getX
    0.81
    x
    0.81
     absc
    0.79
    getX
    0.78
    Activations Density 0.564%

    No Known Activations